3 papers
cs.SD2025
IntMeanFlow: Few-step Speech Generation with Integral Velocity Distillation
Wei Wang, Rong Cao, Yi Guo +3
Flow-based generative models have greatly improved text-to-speech (TTS) synthesis quality, but inference speed remains limited by the iterative sampling process and multiple functi…
cs.CL2025
Seed LiveInterpret 2.0: End-to-end Simultaneous Speech-to-speech Translation with Your Voice
Shanbo Cheng, Yu Bao, Zhichao Huang +25
Simultaneous Interpretation (SI) represents one of the most daunting frontiers in the translation industry, with product-level automatic systems long plagued by intractable challen…
cs.LG2025
SplitMeanFlow: Interval Splitting Consistency in Few-Step Generative Modeling
Yi Guo, Wei Wang, Zhihang Yuan +8
Generative models like Flow Matching have achieved state-of-the-art performance but are often hindered by a computationally expensive iterative sampling process. To address this, r…